Incremental learning of feature space and classifier for face recognition

Ozawa, Seiichi; Toh, Soon Lee; Abe, S.; Pang, Shaoning; Kasabov, Nikola

doi:10.1016/j.neunet.2005.06.016

Cited by 106 publications

(73 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Other approaches to the "stability-plasticity dilemma" were proposed by Polikar et al (2001) and Ozawa et al (2005). Polikar et al (2001) proposed the "Learn++" approach that is based on the boosting (Schapire, 1990) technique.…”

Section: Life-long Learning Architecturesmentioning

confidence: 99%

“…This makes the method unsuitable for our desired interactive learning capability. In contrast to this Ozawa et al (2005) proposed to store representative input-output pairs into a long-term memory for stabilizing an incremental learning radial basis function (RBF) network. Additionally it also accounts for a feature selection mechanism based on incremental principal component analysis, but no classspecific feature selection is applied to efficiently separate co-occurring categories.…”

Section: Life-long Learning Architecturesmentioning

confidence: 99%

See 1 more Smart Citation

A life-long learning vector quantization approach for interactive learning of multiple categories

et al. 2012

View full text Add to dashboard Cite

We present a new method capable of learning multiple categories in an interactive and lifelong learning fashion to approach the "stability-plasticity dilemma". The problem of incremental learning of multiple categories is still largely unsolved. This is especially true for the domain of cognitive robotics, requiring real-time and interactive learning. To achieve the life-long learning ability for a cognitive system, we propose a new learning vector quantization approach combined with a category-specific feature selection method to allow several metrical "views" on the representation space of each individual vector quantization node. These category-specific features are incrementally collected during the learning process, so that a balance between the correction of wrong representations and the stability of acquired knowledge is achieved. We demonstrate our approach for a difficult visual categorization task, where the learning is applied for several complex-shaped objects rotated in depth.

show abstract

Section: Life-long Learning Architecturesmentioning

confidence: 99%

Section: Life-long Learning Architecturesmentioning

confidence: 99%

A life-long learning vector quantization approach for interactive learning of multiple categories

et al. 2012

View full text Add to dashboard Cite

show abstract

“…In the incremental learning phase, the learning algorithm of AL-RAN is basically the same as that of RAN-LTM [7] except that RBF widths are automatically determined or adjusted in an online fashion. Let us explain how RBF widths are determined from incoming data.…”

Section: Incremental Learning Phasementioning

confidence: 99%

“…Although RBFN has mainly been used as batch learning, the significance of its extension to incremental learning is growing from a practical point of view [7,8]. Especially, one-pass incremental learning [9] is an important concept for large-scale high-dimensional data.…”

Section: Introductionmentioning

confidence: 99%

“…This paper is organized as follows. In Section 2, we first give a brief review of Resource Allocating Network with Long-Term Memory (RAN-LTM) [7,14] which gives a classifier model in AL-RAN, and then a new autonomous learning algorithm for AL-RAN is proposed in Section 3. Then, the performance of AL-RAN is evaluated for the five UCI data sets [15] in Section 4.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Autonomous Incremental Learning Algorithm for Radial Basis Function Networks

Ozawa¹,

Tabuchi²,

Nakasaka³

et al. 2010

JILSA

Self Cite

View full text Add to dashboard Cite

In this paper, an incremental learning model called Resource Allocating Network with Long-Term Memory (RAN-LTM)is extended such that the learning is conducted with some autonomy for the following functions: 1) data collection for initial learning, 2) data normalization, 3) addition of radial basis functions (RBFs), and 4) determination of RBF centers and widths. The proposed learning algorithm called Autonomous Learning algorithm for Resource Allocating Network (AL-RAN) is divided into the two learning phases: initial learning phase and incremental learning phase. And the former is further divided into the autonomous data collection and the initial network learning. In the initial learning phase, training data are first collected until the class separability is converged or has a significant difference between normalized and unnormalized data. Then, an initial structure of AL-RAN is autonomously determined by selecting a moderate number of RBF centers from the collected data and by defining as large RBF widths as possible within a proper range. After the initial learning, the incremental learning of AL-RAN is conducted in a sequential

show abstract